IgHHddlZddlmZddlmZddlmZddlmZddl m Z eje Z Gd d eZGd d eZGd deZy)N)Union)PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging)CONFIG_MAPPINGcveZdZdZdZ dfd Zedeee jfddfdZ xZ S) InstructBlipVideoVisionConfiga This is the configuration class to store the configuration of a [`InstructBlipVideoVisionModel`]. It is used to instantiate a InstructBlipVideo vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the InstructBlipVideo [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 1408): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 6144): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. num_hidden_layers (`int`, *optional*, defaults to 39): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. image_size (`int`, *optional*, defaults to 224): The size (resolution) of each image. patch_size (`int`, *optional*, defaults to 14): The size (resolution) of each patch. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"gelu"` are supported. to 1e-5): The epsilon used by the layer normalization layers. layer_norm_eps (`float`, *optional*, defaults to 1e-06): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. initializer_range (`float`, *optional*, defaults to 1e-10): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. qkv_bias (`bool`, *optional*, defaults to `True`): Whether to add a bias to the queries and values in the self-attention layers. Example: ```python >>> from transformers import InstructBlipVideoVisionConfig, InstructBlipVideoVisionModel >>> # Initializing a InstructBlipVideoVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration >>> configuration = InstructBlipVideoVisionConfig() >>> # Initializing a InstructBlipVideoVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration >>> model = InstructBlipVideoVisionModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```instructblipvideo_vision_modelc  t |di| ||_||_||_||_||_||_| |_| |_ ||_ ||_ | |_ y)N) super__init__ hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads patch_size image_sizeinitializer_rangeattention_dropoutlayer_norm_eps hidden_actqkv_bias)selfrrrrrrrrrrrkwargs __class__s /var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/instructblipvideo/configuration_instructblipvideo.pyrz&InstructBlipVideoVisionConfig.__init__Wsi "6"&!2!2#6 $$!2!2,$  pretrained_model_name_or_pathreturnrc >|j||j|fi|\}}|jddk(r|d}d|vrGt|dr;|d|jk7r)t j d|dd|jd|j|fi|S)N model_typeinstructblipvideo vision_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr$loggerwarning from_dictclsr!r config_dicts rfrom_pretrainedz-InstructBlipVideoVisionConfig.from_pretrainedts   (1c112OZSYZ V ??< (,? ?%o6K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r ) i'gelugư>gg|=T __name__ __module__ __qualname____doc__r$r classmethodrstrosPathLiker5 __classcell__rs@rr r "si0 d2J!:4E#r{{BR